可應用於學生專注度之人眼開闔偵測研究

Eye Opening Detection with Application for In-class Attention Monitoring

簡郁菱(Yu-Ling Chien)

指導教授 ： 李忠謀

國立臺灣師範大學/理學院/資訊工程研究所/碩士(2012年)

摘要

本論文提出一個即時的簡易偵測方式，著重於解決遠距離低解析度下，光源與雜訊干擾等問題，能使得眼睛在不同開闔程度下皆能擁有優良的辨識率。
　　藉由使用人臉偵測、局部影像擷取、眼睛區域決策與眼睛區域-可靠度檢查，截取出完整且無遮蔽物的眼睛影像，並且在低解析度時也能明確的找出眼睛位置。再使用簡易、快速且不受光源影響的紋理特徵分佈影像，強化開眼闔眼的對比，得到平順、破碎或群集分佈的二值化影像，分析其中平均值、變異值與分群數的差異，能有效的偵測眼睛狀態。
　　在實驗中可以證明，辨識速率非常的快，在一般複雜環境下表現優異，在遠距離中也並未受到外在環境的干擾。
　　眼睛狀態偵測可搭配人臉偵測與移動偵測，來推廣至學生專注度偵測應用，能有效的辨識出學生專心狀態。

關鍵字

眼睛 ； 人臉偵測 ； 臉部特徵 ； 監控 ； 專注度監控系統 ； 睡意 ； 閉眼 ； 五關位置

並列摘要

This paper proposes a simple real-time method to detect eyes status, which focus on solving the problems of long-range camera, low-resolution image, light and noise interference and different degree of eyes open.
　　By face detection, area of interest, eyes region decision and ER-reliable Decision, we can extract the eyes image without occultation. The methods also can find the position of eyes even with low resolution image. Furthermore, we apply a simple and fast method, texture features of distribution, to make the different status of eyes can be distinguished easily. After above step, we can get a smooth, broken or many clusters of image, which can be analyzed average, variation and the number of clusters to identify the status of eyes.
　　By our experiment result, we can prove that our method can have a fast detection speed, and no matter the environment is under normal condition or low resolution with long distance camera.
　　Therefore, we can use eye detection, face detection and motion detection, to promote a application for in-class attention Monitoring.

並列關鍵字

Eyes ； Face detection ； Facial features ； Monitoring ； Attention monitoring system ； Drowsiness ； Eye closure ； facial features location

參考文獻

[2]　　G. Yang and T. S. Huang, "Human face detection in complex background, " Pattern Recognition, vol. 27, no. 1, pp. 53-63, 1994.

[3]　　K.C. Yow and R. Cipolla, "Feature-Based Human Face Detection," Image and Vision Computing, vol. 15, no. 9, pp. 713-735, 1997.

[4]　　T.K. Leung, M.C. Burl, and P. Perona, "Finding Faces in Cluttered Scenes Using Random Labeled Graph Matching, "Proc. Fifth IEEE Int’l Conf. Computer Vision, pp. 637-644, 1995.

[5]　　Y. Dai and Y. Nakano, "Face-Texture Model Based on SGLD and Its Application in Face Detection in a Color Scene, "Pattern Recognition, vol. 29, no. 6, pp. 1007-1017, 1996.

[6]　　S. McKenna, S. Gong, and Y. Raja, "Modeling Facial Color and Identity with Gaussian Mixtures, "Pattern Recognition, vol. 31, no. 12, pp. 1883-1892, 1998.